Multi-hop question decomposition yields a marginal accuracy edge over direct answering on MQUAKE-T with LLAMA3, both before and after LoRA fine-tuning, but the gains are not statistically validated.
The state of the art in open domain complex question answering: a survey[J]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CL 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Research on Multi-hop Inference Optimization of LLM Based on MQUAKE Framework
Multi-hop question decomposition yields a marginal accuracy edge over direct answering on MQUAKE-T with LLAMA3, both before and after LoRA fine-tuning, but the gains are not statistically validated.